Metraipolis › archive › dc_0200b82525fc

What Makes Agent Memory Useful for Reliable Unanswerable Question Handling? — arXiv:2608.27924

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27924
License (as archived)
CC0-1.0
Archived
2026-10-17T10:56:30.267Z
SHA-256 of the archived text
3cd9394c819622d6fa380806a045896191641c9358ee1977bf55dd8f328eb17f
Stable URL of this page
https://metraipolis.com/documento/dc_0200b82525fc

How to cite

What Makes Agent Memory Useful for Reliable Unanswerable Question Handling? — arXiv:2608.27924 — arXiv (en), https://arxiv.org/abs/2608.27924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0200b82525fc (Metraipolis archive dc_0200b82525fc, sha256 3cd9394c819622d6fa380806a045896191641c9358ee1977bf55dd8f328eb17f)
BibTeX
@misc{dc0200b82525fc,
  title = {What Makes Agent Memory Useful for Reliable Unanswerable Question Handling? — arXiv:2608.27924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0200b82525fc; sha256 3cd9394c819622d6fa380806a045896191641c9358ee1977bf55dd8f328eb17f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Although memory is widely used in agent systems, its role in reliable UAQ handling remains unclear. We present a systematic study of agent memory for UAQ handling under a unified agentic RAG framework, evaluating four representative memory methods across three UAQ-related datasets and two base models. We find that memory can improve UAQ performance in some settings, but such gains are selective rather than universal and remain fragile under dataset shift. Interestingly, cross-model memory reuse is often more feasible than cross-dataset transfer, suggesting that shifts in answerability patterns pose a greater challenge to memory reuse than changes in the base model itself. We further find that UAQ gains are more strongly preserved through decision guidance than through trajectory shaping, and that memory effectiveness depends strongly on representation. In particular, procedural and rule-based memories often provide the most reliable support for UAQ handling, while memory composition is most effective when procedural guidance is combined with complementary behavioral signals. Overall, our findings suggest that reliable UAQ memory depends less on storing larger amounts of experience and more on preserving transferable behavioral guidance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.27924 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T10:47:33.117Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).